Identifying neuroanatomical signatures of anorexia nervosa: a multivariate machine learning approach.

BACKGROUND: There are currently no neuroanatomical biomarkers of anorexia nervosa (AN) available to make clinical inferences at an individual subject level. We present results of a multivariate machine learning (ML) approach utilizing structural neuroanatomical scan data to differentiate AN patients from matched healthy controls at an individual subject level. METHOD: Structural neuroimaging scans were acquired from 15 female patients with AN (age = 20, s.d. = 4 years) and 15 demographically matched female controls (age = 22, s.d. = 3 years). Neuroanatomical volumes were extracted using the FreeSurfer software and input into the Least Absolute Shrinkage and Selection Operator (LASSO) multivariate ML algorithm. LASSO was 'trained' to identify 'novel' individual subjects as either AN patients or healthy controls. Furthermore, the model estimated the probability that an individual subject belonged to the AN group based on an individual scan. RESULTS: The model correctly predicted 25 out of 30 subjects, translating into 83.3% accuracy (sensitivity 86.7%, specificity 80.0%) (p < 0.001; χ 2 test). Six neuroanatomical regions (cerebellum white matter, choroid plexus, putamen, accumbens, the diencephalon and the third ventricle) were found to be relevant in distinguishing individual AN patients from healthy controls. The predicted probabilities showed a linear relationship with drive for thinness clinical scores (r = 0.52, p < 0.005) and with body mass index (BMI) (r = -0.45, p = 0.01). CONCLUSIONS: The model achieved a good predictive accuracy and drive for thinness showed a strong neuroanatomical signature. These results indicate that neuroimaging scans coupled with ML techniques have the potential to provide information at an individual subject level that might be relevant to clinical outcomes.

Naturalistic follow-up of subjects affected with anorexia nervosa 8 years after multimodal treatment: Personality and psychopathology changes and predictors of outcome.

BACKGROUND: Eating disorders (EDs) are serious mental illnesses of growing clinical and social impact. Despite their severity, there is still no satisfactory evidence-based treatment. Follow-up investigations are the most reliable studies to enlighten long-term outcome predictors and modifiers. METHODS: In total, 59 subjects affected with anorexia nervosa were assessed 8 years after their admission into an outpatient multimodal treatment program for eating disorders. The follow-up changes in diagnostic criteria were compared with Chi-square test. Improved and not-improved subjects were compared. Clinical, personality and psychopathology features between T0 and T1 were compared with t-test for repeated measures. Correlation between T0 features and changes at T1 in personality and psychopathology features were assessed. RESULTS: The rate of complete remission was 42%, an overall rate of 67.8% improved, a rate of 18.6% worsened. Concerning personality, a significant decrease of harm avoidance and increase in self-directedness were evidenced. Interoceptive awareness, drive for thinness, bulimia were significantly reduced at follow-up. Many T0 personality facets were related to personality and psychopathology improvement at follow-up. CONCLUSION: Multimodal treatment encompassing psychiatric, nutritional and psychological approaches is at the moment the most reliable approach for the treatment of moderate to severe anorexia nervosa with a discrete rate of improvement. Some personality and psychopathology characteristics may represent specific factors which favor resistance and impair improvement. Future approaches should consider the personalization of therapeutic approach according to these features.